CN104182297A - Method and system used for recovery from failure of primary storage volumes - Google Patents
Method and system used for recovery from failure of primary storage volumes Download PDFInfo
- Publication number
- CN104182297A CN104182297A CN201410220136.3A CN201410220136A CN104182297A CN 104182297 A CN104182297 A CN 104182297A CN 201410220136 A CN201410220136 A CN 201410220136A CN 104182297 A CN104182297 A CN 104182297A
- Authority
- CN
- China
- Prior art keywords
- storage controller
- main frame
- timestamp
- time
- primary storage
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Granted
Links
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F3/00—Input arrangements for transferring data to be processed into a form capable of being handled by the computer; Output arrangements for transferring data from processing unit to output unit, e.g. interface arrangements
- G06F3/06—Digital input from, or digital output to, record carriers, e.g. RAID, emulated record carriers or networked record carriers
- G06F3/0601—Interfaces specially adapted for storage systems
- G06F3/0628—Interfaces specially adapted for storage systems making use of a particular technique
- G06F3/0646—Horizontal data movement in storage systems, i.e. moving data in between storage devices or systems
- G06F3/065—Replication mechanisms
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F11/00—Error detection; Error correction; Monitoring
- G06F11/07—Responding to the occurrence of a fault, e.g. fault tolerance
- G06F11/14—Error detection or correction of the data by redundancy in operation
- G06F11/1402—Saving, restoring, recovering or retrying
- G06F11/1446—Point-in-time backing up or restoration of persistent data
- G06F11/1448—Management of the data involved in backup or backup restore
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F11/00—Error detection; Error correction; Monitoring
- G06F11/07—Responding to the occurrence of a fault, e.g. fault tolerance
- G06F11/16—Error detection or correction of the data by redundancy in hardware
- G06F11/20—Error detection or correction of the data by redundancy in hardware using active fault-masking, e.g. by switching out faulty elements or by switching in spare elements
- G06F11/2053—Error detection or correction of the data by redundancy in hardware using active fault-masking, e.g. by switching out faulty elements or by switching in spare elements where persistent mass storage functionality or persistent mass storage control functionality is redundant
- G06F11/2056—Error detection or correction of the data by redundancy in hardware using active fault-masking, e.g. by switching out faulty elements or by switching in spare elements where persistent mass storage functionality or persistent mass storage control functionality is redundant by mirroring
- G06F11/2071—Error detection or correction of the data by redundancy in hardware using active fault-masking, e.g. by switching out faulty elements or by switching in spare elements where persistent mass storage functionality or persistent mass storage control functionality is redundant by mirroring using a plurality of controllers
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F3/00—Input arrangements for transferring data to be processed into a form capable of being handled by the computer; Output arrangements for transferring data from processing unit to output unit, e.g. interface arrangements
- G06F3/06—Digital input from, or digital output to, record carriers, e.g. RAID, emulated record carriers or networked record carriers
- G06F3/0601—Interfaces specially adapted for storage systems
- G06F3/0602—Interfaces specially adapted for storage systems specifically adapted to achieve a particular effect
- G06F3/0614—Improving the reliability of storage systems
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F3/00—Input arrangements for transferring data to be processed into a form capable of being handled by the computer; Output arrangements for transferring data from processing unit to output unit, e.g. interface arrangements
- G06F3/06—Digital input from, or digital output to, record carriers, e.g. RAID, emulated record carriers or networked record carriers
- G06F3/0601—Interfaces specially adapted for storage systems
- G06F3/0668—Interfaces specially adapted for storage systems adopting a particular infrastructure
- G06F3/0671—In-line storage system
- G06F3/0683—Plurality of storage devices
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F2201/00—Indexing scheme relating to error detection, to error correction, and to monitoring
- G06F2201/82—Solving problems relating to consistency
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F2201/00—Indexing scheme relating to error detection, to error correction, and to monitoring
- G06F2201/835—Timestamp
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Human Computer Interaction (AREA)
- Quality & Reliability (AREA)
- Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
Abstract
A primary storage controller receives an input/output (I/O) command from a host, wherein a host timestamp is associated with the I/O command. During a mirroring of storage volumes to a secondary storage controller, the primary storage controller communicates the host timestamp associated with the I/O command to the secondary storage controller, wherein mirrored copies of the storage volumes are timestamped based on at least the host timestamp and an elapsed time since a last host I/O command. A recovery is made from a failure of one or more of the storage volumes in the primary storage controller, by using the timestamped mirrored copies of the storage volumes.
Description
Technical field
Embodiment relates to by using the mirror image data of safeguarding with main frame timestamp to recover from the fault of primary storage volume.
Embodiment
In the following description, with reference to forming a part for instructions and the accompanying drawing of several embodiment being shown.Should be appreciated that and can utilize other embodiment and can carry out structure and operational change.
No match time between main frame and primary storage controller
In certain embodiments, can indicate with the mutual main frame of primary storage controller the time that is different from this indicated time of primary storage controller.In some cases, the backup copies (mirror image copies of the data of, storing in this primary storage controller) of being stored by auxiliary storage controller can add timestamp with the indicated time of the clock of primary storage controller.If mirror image copies added timestamp with the indicated time of the clock of primary storage controller,, the in the situation that of Disaster Recovery Project for Short, main frame may not determine which time point to carry out the I/O having lost from operates by the timestamp mirror image copies.Result is that disaster recovery can require to check the journal file of storing the I/O operation being performed.
In certain embodiments, the mirror image copies of the data of storing in auxiliary storage controller is added timestamp, so that instruction instead of the auxiliary storage controller time of main frame time to be provided.In these embodiments, because main frame is known I/O operation and is had to again, from the time of its execution, therefore to carry out disaster recovery from the mirror image copies of data obviously faster.
Exemplary embodiment
Fig. 1 illustrates comprising and the block diagram of the computing environment 100 of the primary storage controller 102 of 104 one-tenth mirrors of auxiliary storage controller according to some embodiment.
According to some embodiment, primary storage controller 102 is coupled to multiple main frame 106a ... 106n, and auxiliary storage controller 104 is coupled to multiple main frame 108a ... 108m.
Memory controller 102,104 and main frame 106a ... 106n, 108a ... 108m can comprise any suitable computing equipment, comprise current known computing equipment in this area, such as personal computer, workstation, server, large scale computer, handheld computer, palmtop computer, telephone plant, network home appliance, blade type computer etc.Primary storage controller 102 can be coupled to memory device 110 and auxiliary storage controller 104 can be coupled to memory device 112, wherein, these memory devices can comprise any suitable memory device, comprise current known memory device in this area, such as disk, CD, tape etc.In certain embodiments, main frame 106a ... 106n, 108a ... 108m, memory controller 102,104 and memory device 110,112 can be coupled by network, such as the Internet, Intranet, storage area network, LAN (Local Area Network) etc.
Primary storage controller 102 and auxiliary storage controller 104 can be controlled multiple storage volume, and wherein, these storage volume are logical expressions of the physical store of maintenance in memory device 110,112.The data of storing in these storage volume can represent with magnetic track, section or some other storage cells.
Auxiliary storage controller 102 comprises memory image application 116, and wherein this memory image application can also be called as mirror image application.
In certain embodiments, main frame 106a can send to primary storage controller 102 by the I/O operation that is marked with timestamp 118, operates (for example, read or write) to carry out the I/O to storage volume being controlled by primary storage controller 102.Memory image application 116 can be carried out memory image by storage volume is replicated asynchronously to auxiliary storage controller 104 from primary storage controller 102.Asynchronous replication means that storage is rolled onto copying of auxiliary storage controller 104 and does not wait for that main frame I/O operates in before copying and complete, that is, storage volume is independent of completing of main frame I/O operation from primary storage controller 102 to copying of auxiliary storage controller 104.
In certain embodiments, when consistance group in auxiliary storage controller 104 in the time that a time point forms, auxiliary storage controller 104 execution time points replication application 122 are with the storage volume of synchronous copy consistency group.The storage volume of the consistance group of time point when data are recovered to form from consistance group realizes.Form consistance group to prevent being written in from main frame 106a unordered the inconsistent copy that creates storage volume during asynchronous replication 120.
Primary storage controller 102 has primary storage controller clock or indicated time of some other mechanisms, and this time is called as the primary storage controller time 124.The primary storage controller time 124 can be different from the time in main frame 106a.For example, at synchronization, the time of main frame 106a can be 12:03:13PM, and the time of primary storage controller 102 can be 12:03:43PM.In addition, in primary storage controller 102, can there is clock drift.In other words, primary storage controller clock 124 can not ensure that 100% is accurate.In fact, most of digital dock have " drift ", even very little.Therefore,, if host clock and primary storage controller clock are synchronous in some day, due to the clock drift of primary storage controller clock, their can have slight asynchronous behind 6 months from that day.
In certain embodiments, in the disaster recovery scene of losing primary storage volume, the time point can be used to the recovering state of these storage volume to form to consistance group from the time point copy of auxiliary storage controller 104 time.In certain embodiments, during being that a time point forms the mirror sessions of consistance group, in auxiliary storage controller 104, these time point copies of storage carry out mark with the timestamp of the time based on main frame 106a (time that forms main frame I/O operation last time comprising by consistance group indicates), the elapsed time of auxiliary storage controller 104 and the drift of primary storage controller 102.
Fig. 2 illustrate according to some embodiment, how explanation to generate asynchronous remote copy and time point copy and the block diagram 200 of application time stamp how during data image.
Fig. 2 illustrates three volumes, is called as volume A202, volume B204 and volume C206.Volume A202 is controlled by primary storage controller 102, and volume B204 and C206 are controlled by auxiliary storage controller 104.
In certain embodiments, volume A202 is replicated asynchronously to volume B204 by the memory image application 116 of carrying out in primary storage controller 102.In the time that the consistance copy of storage volume set has generated by asynchronous replication 208 in auxiliary storage controller 104, point in time copy application 122 is generated to the time point copy (, instantaneous synchronization counterpart) of volume B204 in volume C206.Time point copy be with based on last time I/O time of main frame time add timestamp, the main frame time of I/O last time is adjusted and further adjusted according to the potential drift of the time of primary storage controller 102 (Reference numeral 210) according to the elapsed time of measuring in primary storage controller 102.Therefore, this time point copy at least adds timestamp based on the main frame time.
Fig. 3 illustrate according to some embodiment, how explanation operate main frame timestamp and I/O and be associated and which main frame how mirror sessions to indicate have the block diagram 300 of mirror sessions.
In certain embodiments, in the time that I/O operation 302 is sent to auxiliary storage controller 102 by main frame 106a, main frame timestamp 304 is also associated with I/O operation 302, and the I/O order of these types can be called as the I/O operation 306 of enhancing.
In the time that mirror sessions starts, the designator 308 in primary storage controller 102 is associated mirror sessions with the main frame that has this mirror sessions.Because these I/O are marked with main frame timestamp, therefore mirror sessions know from main frame 106a last time I/O time, and from main frame 106a last time I/O time for the time point copy of auxiliary storage controller 104 storage is added timestamp.
Fig. 4 illustrates according to the explanation of some embodiment first and operates 400 process flow diagram.Operation shown in Fig. 4 can be carried out in computing environment 100.
Control starts from frame 402, and wherein, the I/O request of the timestamp that is supplemented with the instruction main frame time is sent to primary storage controller 102 by main frame 106a.The memory image application 116 of carrying out in primary storage controller 102 by one or more storage volume from primary storage controller 102 asynchronous replication (frame 404) to auxiliary storage controller 104.
Control proceeds to frame 406, wherein, once primary storage controller 102 knows each in auxiliary storage controller 104 and roll up in a time point unanimously with the each volume in primary storage controller 102, auxiliary storage controller 104 is just carried out the point in time copy of the storage volume to consistance group.Point in time copy operation using as calculated, (frame 408 places) were associated with these time point copies according to the time of the potential drift adjusted main frame time of primary storage controller 102.
Fig. 5 illustrates according to the explanation of some embodiment second and operates 500 process flow diagram.Operation shown in Fig. 5 can be carried out in computing environment 100.
Control starts from frame 502, and wherein, the one or more storage volume in primary storage controller 102 break down.Main frame 106a is by attempting (frame 504 places) Recovery processing with the time point copy of storage in auxiliary storage controller 104.Because these time point copies are marked with the timestamp of reflection main frame time, therefore main frame 106a regenerates all operations were that (frame 506 places) have completed since indicated timestamp in these time point copies.
Fig. 6 illustrates the block diagram 600 of time when these time point copies of storage in auxiliary storage controller 104 being added timestamp according to the explanation how to confirm of some embodiment.
The operational main frame timestamp of main frame I/O last time (Reference numeral 602) is known (Reference numeral 604), and because mirror sessions has the main frame that is associated that has this mirror sessions, therefore each main frame I/O adds timestamp with this information.Elapsed time 604 in primary storage controller 102 since main frame I/O operation last time is also known, and wherein, the elapsed time is to measure by the clock of primary storage controller 102.The clock of primary storage controller also may have drift 606 (for example, the time shown in clock may be during the elapsed time potentially drift depart from .05 second).Time when time point copy being added timestamp in order calculating, the operational main frame timestamp 602 of main frame I/O last time and the elapsed time 604 in primary storage controller 102 since main frame I/O operation last time to be added, and to have deducted drift 606.Therefore, ensure that the actual main frame time is at least equaling or prior to the calculated time for time point copy is added timestamp.For example, the time of calculating can be 7PM, and the actual host time can be 7:01PM.But in the time that the calculated time is 7PM, the actual host time can not be 6:55PM.It should be noted that during mirror image, primary storage controller 102 can send to temporal information auxiliary storage controller 104 so that these mirror image copies of storage in auxiliary storage controller 104 are added timestamp.
Fig. 7 illustrates according to the process flow diagram of the explanation of some embodiment the 3rd operation 700.Operation shown in Fig. 7 can be carried out in computing environment 100.
Control starts from frame 702, and wherein, primary storage controller 102 receives I/O (I/O) order from main frame 106a, and wherein main frame timestamp is associated with I/O order.Be rolled onto the mirror image of auxiliary storage controller 104 in storage during, the main frame timestamp being associated with I/O order is sent to auxiliary storage controller 104 by primary storage controller 102, wherein, the mirror image copies of these storage volume is (frames 704) that at least added timestamp based on main frame timestamp and the elapsed time since main frame I/O order last time.
Control proceeds to frame 706, wherein, by using the mirror image copies that is added with timestamp of storage volume, in the one or more fault in the storage volume from primary storage controller, recovers.
Therefore, Fig. 1-7 show some embodiment, wherein by with the main frame time, mirror image copies being added timestamp, than the situation that wherein mirror image copies added timestamp with the time of memory controller, from the fault of primary storage volume, recover sooner.
The further details of some embodiment
In some z/OS* configurations, to expect to use Global Mirror* (global mirror, GM), i.e. memory image, is also referred to as mirror image.In the situation that there is disaster, for the copy of re-synchronization working load, control software need to be understood consistance group and when form.Problem is, from the consistance group timestamp of mirror image with respect to system synthesis body (sysplex) clock, and global mirror consistance timestamp is with respect to DS8K* (a class memory controller) clock, and between the two, there is no association.
In order to make the global mirror consistance time meaningful to managed storage, in the time forming consistance group, global mirror can be used the system synthesis body time of estimation.This time can be used as and can distribute at Flashcopy* (, the time point copy) sequence number of disaster recovery site place inquiry.In order to realize this point, need the following:
1) Global Mirror session need to know it to be tied to which system synthesis body; And
2) Global Mirror session need to be known the current system synthesis body time.
The system synthesis body time is to provide in the I/O of the host computer system from system synthesis body.Most of I/O are carrying system synthesis timestamp.Timestamp in these I/O is used to keep DS8K and system synthesis body clock synchronous.Do not have method to ensure that the each I/O that enters specific DS8K is from same system synthesis.Therefore it is unsafe, selecting at random which I/O to carry out the check system synthesis time.In order to determine whether I/O has carried the correct system synthesis body time, the mode whether DS8K needs proving time stamp to be generated by the system synthesis body of expecting.In order to realize this point, system synthesis body can provide system synthesis body title in initialization system characteristic (SSC) data structure.Based on each I/O, the system synthesis body title in SSC and the system synthesis body title that offers GM session can be compared to judge whether the time in I/O can be used as the system synthesis body time of session.
When by the memory controller sequence of calculation number (timestamp), it never should be greater than time (clock by it is indicated) of synchronization on main frame.Time a little is early fine, because it will only require some data that may needn't recover to be resumed.This is by always supposing the maximum drift of memory controller and host clock and realizing in memory controller in the memory controller computing interval.
Some embodiment processes the drift between DS8K and system synthesis body clock.Even some embodiment arbitrary long-time in receiving from system synthesis body, also continue the estimating system synthesis time.In addition, consider that main frame can provide the clock form unique for given main frame, some embodiment dynamic calculation DS8K clock form.
Consider that some embodiment can have multiple GM sessions, exist each GM session can there is the requirement of the unique main frame that has it.The timestamp that each session can store and only receive based on the main frame from having independently carrys out stamp computing time.
In certain embodiments, in the time of client definition Global Mirror session, require they by initiation command provide instruction they want to use the timestamp of main frame or the old DS8K timestamp mark for their copy sequence number (being timestamp).These FlashCopy sequence number designation datas are with when consistent.If they indicate them to want to use the timestamp of main frame, also require client to input Global Mirror session and will accept the host name of timestamp from it.
Additional embodiment details
The operation described may be embodied as and uses standard program and/or engineering to produce method, device or the computer program of software, firmware, hardware or any combination wherein.Therefore, the each side of these embodiment can take the embodiment that entirety is hardware, the overall embodiment (comprising firmware, resident software, microcode etc.) for software or combination to have the form of the embodiment of software and hardware aspect, can be all referred to as " circuit ", " module " or " system " these these.In addition, the each side of these embodiment can take to be included in the form of the computer program in one or more computer-readable mediums with the computer readable program code that is contained in it.
Can adopt the combination in any of one or more computer-readable mediums.Computer-readable medium can be computer-readable signal media or computer-readable recording medium.Computer-readable recording medium can be, such as but not limited to electricity, magnetic, optical, electrical magnetic, infrared ray or semi-conductive system, device or device, or aforesaid any appropriately combined.The example more specifically (non exhaustive list) of computer-readable recording medium can comprise following: electrical connection, portable computer diskette, hard disk, random access memory (RAM), ROM (read-only memory) (ROM), erasable type programmable read only memory (EPROM or flash memory), optical fiber, read-only optical disc (CD-ROM), light storage device, the magnetic memory device or aforesaid any appropriately combined with one or more wires.In the context of the literature, computer-readable recording medium can be any comprising or stored program tangible medium, and program can be used or be combined with it by instruction execution system, device or device.
Computer-readable signal media can be included in the data-signal of propagating in base band or as a part for carrier wave, has wherein carried computer-readable program code.The combination of electromagnetic signal that the data-signal of this propagation can adopt various ways, comprises---but being not limited to---, light signal or above-mentioned any appropriate.Computer-readable signal media can also be any computer-readable medium beyond computer-readable recording medium, and this computer-readable medium can send, propagates or transmit the program for being used or be combined with it by instruction execution system, device or device.
The program code comprising on computer-readable medium can be with any suitable medium transmission, comprises that---but being not limited to---is wireless, wired, optical cable, RF etc., or the combination of above-mentioned any appropriate.
Can write the computer program code for carrying out the present invention's operation with the combination in any of one or more programming languages, described programming language comprises object-oriented programming language-such as Java, Smalltalk, C++ etc., also comprises conventional process type programming language-such as " C " language or similar programming language.Program code can fully be carried out, partly on subscriber computer, carries out, carry out or on remote computer or server, carry out completely as an independently software package execution, part part on subscriber computer on remote computer on subscriber computer.In the situation that relates to remote computer, remote computer can be by the network of any kind---comprise LAN (Local Area Network) (LAN) or wide area network (WAN)-be connected to subscriber computer, or, can be connected to outer computer (for example utilizing ISP to pass through Internet connection).
Below with reference to describing the present invention according to process flow diagram and/or the block diagram of the method for the embodiment of the present invention, device (system) and computer program.Should be appreciated that the combination of each square frame in each square frame of process flow diagram and/or block diagram and process flow diagram and/or block diagram, can be realized by computer program instructions.These computer program instructions can offer the processor of multi-purpose computer, special purpose computer or other programmable data treating apparatus, thereby produce a kind of machine, make these computer program instructions in the time that the processor by computing machine or other programmable data treating apparatus is carried out, produced the device of the function/action specifying in the one or more square frames in realization flow figure and/or block diagram.
Also these computer program instructions can be stored in computer-readable medium, these instructions make computing machine, other programmable data treating apparatus or miscellaneous equipment with ad hoc fashion work, thereby the instruction being stored in computer-readable medium just produces the manufacture (article of manufacture) of the instruction of the function/action specifying in the one or more square frames that comprise in realization flow figure and/or block diagram.
Computer program instructions can also be loaded in computing machine, other programmable data treating apparatus or miscellaneous equipment and produce computer-implemented processing so that sequence of operations step is carried out on computing machine, other programmable device or miscellaneous equipment, and these instructions of consequently carrying out on computing machine, other programmable device are provided for the processing of the function/action of specifying in the one or more frames in implementing procedure figure and/or block diagram.
Fig. 8 illustrate according to some embodiment, explanation can be included in memory controller 102,104 or main frame 106a ... 106n, 108a ... some element in 108m block diagram.System 800 can comprise circuit 802, and circuit 802 can comprise at least one processor 804 in certain embodiments.System 800 can also comprise storer 806 (for example, volatile memory device) and memory device 808.Memory device 808 can comprise non-volatile memory devices (for example, EEPROM, ROM, PROM, RAM, DRAM, SRAM, flash memory, firmware, FPGA (Field Programmable Gate Array) etc.), disk drive, disc drives, magnetic tape drive etc.Memory device 808 can comprise that internal storage device, affixed storage device and/or network can be accessed by memory device.System 800 can comprise programmed logic 810, and programmed logic 810 comprises can be loaded into the code 812 of carrying out in storer 806 and by processor 804 or circuit 802.In certain embodiments, the programmed logic 810 that comprises code 812 can be stored in memory device 808.In certain embodiments, programmed logic 810 can be implemented in circuit 802.Therefore, be independent of other element although Fig. 8 illustrates programmed logic 810, programmed logic 810 can be implemented in storer 806 and/or circuit 802.
Some embodiment can be for a kind of method that for processing integrated computer readable code by people or robotization, computations is deployed to computing system, and wherein, described code can be carried out these operations of described embodiment together with computing system.
Unless expressly stated otherwise,, otherwise term " embodiment ", " embodiment ", " each embodiment ", " described embodiment ", " these embodiment ", " one or more embodiment ", " some embodiment " and " embodiment " mean " one or more (not whole) embodiment of this (respectively) invention ".
Unless expressly stated otherwise,, otherwise term " comprises ", " comprising ", " having " and similar terms thereof mean " including but not limited to ".
Unless expressly stated otherwise,, otherwise the bulleted list of enumerating does not imply any or all of project is mutually exclusive.
Unless expressly stated otherwise,, otherwise term " (a) ", " one (an) " and " described (the) " mean " one or more ".
Unless expressly stated otherwise,, otherwise the equipment communicating with one another needn't communicate with one another continuously.In addition, the equipment communicating with one another can directly or indirectly be communicated by letter by one or more media.
Description to the embodiment with the several parts that communicate with one another does not imply that all these parts are necessary.On the contrary, described various selectable unit (SU)s various possible embodiment of the present invention has been described.
Further, although described in order various processes, method step, algorithm etc., these processing, method and algorithm can carry out work with alternative arranged in order.In other words, described any sequence of steps or order might not instruction these steps in ground be carried out with that order.These treatment steps described herein can be carried out with the order of any practicality.Further, some steps can be carried out simultaneously.
In the time having described individual equipment or article here, it is evident that, can use multiple equipment/article (no matter whether they cooperate) to replace individual equipment/article.Similarly, here describe in the situation of more than one equipment or article (no matter whether they cooperate), it is evident that, can replace multiple equipment or article with individual equipment/article, or, equipment or the program of number shown in can replacing with the equipment/article of different numbers.One or more miscellaneous equipments that the function of equipment and/or feature can alternately be clearly described as having this function/feature comprise.Therefore, other embodiments of the invention needn't comprise equipment itself.
Some event of at least some operation instructions that may illustrate in the drawings occurs in sequence with a certain.In alternative embodiment, some operation can be performed, be modified or be removed with different orders.In addition, step can be added to above-described logic, and still meet described embodiment.Further, operation described herein can occur in sequence, or some operation can be by parallel processing.Again, each operation can or be carried out by distributed processing unit by single processing unit.
Present the aforementioned description of various embodiments of the invention for the purpose of illustration and description.Intention is not exhaustive or to limit the invention to disclosed accurate form.According to instruction above, it is possible much revising and changing.Be intended that, scope of the present invention is not to be limited by detailed description, but is limited by appended claim.Appointment, example and data above provide to the present invention form manufacture and the complete description of use.Because a lot of embodiment of the present invention can implement and not deviate from the spirit and scope of the present invention, the present invention is present in appended thereafter claim.
* Java is trade mark or the registered trademark of Oracle and/or its subsidiary corporation.
* z/OS, Global Mirror, Flashcopy, DS8K are trade mark or the registered trademarks of IBM Corporation.
Background technology
The data image of some type provides remote data Replica between two websites for business continuance and disaster recovery.This data image can provide and be low to moderate 1-5 second or recovery point objectives still less (RPO) between remote two websites, and this application to home site place has small or there is no a performance impact.This mirror image copy data asynchronously, and form consistance group with conventional interval, thus allow the recovery completely of application.
In some cases, this mirror image can be realized by the combination of remote asynchronous remote copy and point in time copy.In asynchronous remote copy, storage volume is replicated asynchronously to auxiliary storage controller from primary storage controller.Once form consistance group during asynchronous remote copy, just execution time point replicate run in auxiliary storage controller.Point in time copy is the complete available copies that the defined data that comprise the mirror image of data in the time that it appears at single time point are collected.This copy is considered to occur in logic at this time point place.As long as result is the consistance copies of these data in the time that it appears at this time point, embodiment just can carried out the part or all of of this copy At All Other Times.
Summary of the invention
A kind of method, system and computer program are provided, and wherein, primary storage controller receives I/O (I/O) order from main frame, and wherein main frame timestamp is associated with described I/O order.Be rolled onto the mirror image of auxiliary storage controller in storage during, the described main frame timestamp being associated with described I/O order is sent to described auxiliary storage controller by described primary storage controller, and the described mirror image copies of wherein said storage volume has at least added timestamp based on described main frame timestamp and the elapsed time since main frame I/O order last time.By using the mirror image copies that is added with timestamp of described storage volume, in the fault of the one or more storage volume in the described storage volume from described primary storage controller, recover.
In certain embodiments, the clock in described main frame and described primary storage controller are indicated the different time.
In a further embodiment, than having the only timestamp of the clock based on described primary storage controller, in the time that described mirror image copies at least adds timestamp based on described main frame timestamp, from the fault of described primary storage controller, recovering is faster.
In embodiment further, described mirror image comprises from described primary storage controller and operates to form consistance group to the asynchronous replication of described auxiliary storage controller, and in response to the synchronizing time point replicate run that forms consistance group in described auxiliary storage controller.
In additional embodiment, the described mirror image copies of described storage volume is also added timestamp to the drift of error based on being included in the described elapsed time of measuring in described primary storage controller, and be wherein sent to described auxiliary storage controller by the time of described primary storage controller instruction.
In a further embodiment, described main frame is not queried to determine the time on described main frame, and the described time of described main frame is that described main frame timestamp by being associated with described I/O order provides.
Brief description of the drawings
Referring now to accompanying drawing, wherein same Reference numeral represents corresponding parts from start to finish:
Fig. 1 illustrates the block diagram that becomes the computing environment of the primary storage controller of mirror with auxiliary storage controller that comprises according to some embodiment;
Fig. 2 illustrates according to the explanation of some embodiment how during data image, to generate asynchronous remote copy and time point copy and the block diagram of application time stamp how;
Fig. 3 illustrates according to the explanation of some embodiment and how main frame timestamp is associated with I/O operation and which main frame how mirror sessions to indicate have the block diagram of this mirror sessions;
Fig. 4 illustrates the process flow diagram operating according to the explanation of some embodiment first;
Fig. 5 illustrates the process flow diagram operating according to the explanation of some embodiment second;
Fig. 6 illustrates the block diagram how time point copy being added timestamp according to the explanation of some embodiment;
Fig. 7 illustrates according to the process flow diagram of the explanation of some embodiment the 3rd operation;
Fig. 8 illustrates the block diagram that can be included in the computing system of some element in primary storage controller or auxiliary storage controller or the arbitrary main frame of Fig. 1 according to the explanation of some embodiment.
Claims (14)
1. the method for recovering from the fault of primary storage volume, comprising:
In primary storage controller, receive I/O (I/O) order from main frame, wherein main frame timestamp is associated with described I/O order;
Be rolled onto the mirror image of auxiliary storage controller in storage during, by described primary storage controller, the described main frame timestamp being associated with described I/O order is sent to described auxiliary storage controller, the described mirror image copies of wherein said storage volume has at least added timestamp based on described main frame timestamp and the elapsed time since main frame I/O order last time; And
By using the described mirror image copies that is added with timestamp of described storage volume, in the fault of the one or more storage volume in the described storage volume from described primary storage controller, recover.
2. method according to claim 1, the clock in wherein said main frame and described primary storage controller are indicated the different time.
3. method according to claim 2, wherein than thering is the only timestamp of the clock based on described primary storage controller, in the time that described mirror image copies at least adds timestamp based on described main frame timestamp, from the fault of described primary storage controller, recovering is faster.
4. method according to claim 1, wherein said mirror image comprises:
Asynchronous replication operation from described primary storage controller to described auxiliary storage controller, to form consistance group; And
In response to the synchronizing time point replicate run that forms consistance group in described auxiliary storage controller.
5. method according to claim 1, wherein also adds timestamp the drift of error based on being included in the described elapsed time of measuring in described primary storage controller to the described mirror image copies of described storage volume.
6. method according to claim 1, the clock of wherein said elapsed time based on described primary storage controller, and the wherein said indicated time of primary storage controller be sent to described auxiliary storage controller.
7. method according to claim 1, does not wherein inquire about described main frame to determine the time on described main frame, and the described time of described main frame is that described main frame timestamp by being associated with described I/O order provides.
8. the system for recovering from the fault of primary storage volume, comprising:
The module that is configured to receive I/O (I/O) order in primary storage controller, wherein main frame timestamp is associated with described I/O order;
Be configured to during storage is rolled onto the mirror image of auxiliary storage controller, by described primary storage controller, the described main frame timestamp being associated with described I/O order be sent to the module of described auxiliary storage controller, the mirror image copies of wherein said storage volume has at least added timestamp based on described main frame timestamp and the elapsed time since main frame I/O order last time; And
Be configured to the module of recovering in the fault of the one or more storage volume in the described storage volume from described primary storage controller by the described mirror image copies that is added with timestamp by described storage volume.
9. system according to claim 8, the clock in wherein said main frame and described primary storage controller are indicated the different time.
10. system according to claim 9, wherein than thering is the only timestamp of the clock based on described primary storage controller, in the time that described mirror image copies at least adds timestamp based on described main frame timestamp, from the fault of described primary storage controller, recovering is faster.
11. systems according to claim 8, wherein said mirror image comprises:
Asynchronous replication operation from described primary storage controller to described auxiliary storage controller, to form consistance group; And
In response to the synchronizing time point replicate run that forms consistance group in described auxiliary storage controller.
12. systems according to claim 8, wherein also add timestamp the drift of error based on being included in the described elapsed time of measuring in described primary storage controller to the described mirror image copies of described storage volume.
13. systems according to claim 8, the clock of wherein said elapsed time based on described primary storage controller, and the wherein said indicated time of primary storage controller be sent to described auxiliary storage controller.
14. systems according to claim 8, wherein do not inquire about described main frame to determine the time on described main frame, and the described time of described main frame is that described main frame timestamp by being associated with described I/O order provides.
Applications Claiming Priority (2)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| US13/901,082 US9280296B2 (en) | 2013-05-23 | 2013-05-23 | Recovery from failure of primary storage volumes by using mirrored data maintained with host timestamps |
| US13/901,082 | 2013-05-23 |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN104182297A true CN104182297A (en) | 2014-12-03 |
| CN104182297B CN104182297B (en) | 2017-10-13 |
Family
ID=51936196
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201410220136.3A Expired - Fee Related CN104182297B (en) | 2013-05-23 | 2014-05-22 | For the method and system recovered from the failure of primary storage volume |
Country Status (2)
| Country | Link |
|---|---|
| US (1) | US9280296B2 (en) |
| CN (1) | CN104182297B (en) |
Families Citing this family (14)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US9898374B2 (en) * | 2014-04-08 | 2018-02-20 | International Business Machines Corporation | Recovery of an infected and quarantined file in a primary storage controller from a secondary storage controller |
| US9665308B2 (en) * | 2015-03-10 | 2017-05-30 | International Business Machines Corporation | Optimization of the copying of change recorded data by using spare flash capacity |
| US10341211B2 (en) * | 2015-09-25 | 2019-07-02 | Brocade Communications Systems LLC | Command response and completion determination |
| US10423500B2 (en) * | 2016-06-01 | 2019-09-24 | Seagate Technology Llc | Technologies for limiting performance variation in a storage device |
| US10338834B1 (en) * | 2016-09-29 | 2019-07-02 | Veritas Technologies Llc | Application performance in replication environments |
| US10241698B2 (en) * | 2017-03-24 | 2019-03-26 | International Business Machines Corporation | Preservation of a golden copy that stores consistent data during a recovery process in an asynchronous copy environment |
| US10289322B2 (en) * | 2017-06-01 | 2019-05-14 | International Business Machines Corporation | Delayed consistent point-in-time copy from a secondary volume of a consistent asynchronous mirror copy |
| US10229180B2 (en) | 2017-06-01 | 2019-03-12 | International Business Machines Corporation | Consistent point-in-time copy of a consistent asynchronous mirror target without pausing a consistent asynchronous mirror copy |
| US11379335B2 (en) | 2017-10-05 | 2022-07-05 | International Business Machines Corporation | Self-reporting remote copy performance on a consistency group |
| US10564863B2 (en) | 2018-04-24 | 2020-02-18 | International Business Machines Corporation | Identifying an availability of a system |
| CN110688251B (en) * | 2018-07-05 | 2021-12-31 | 华为技术有限公司 | Data writing method and storage system |
| US11055013B2 (en) | 2019-01-25 | 2021-07-06 | International Business Machines Corporation | Recovering from data loss using copy services relationships between volumes |
| US11055017B1 (en) | 2020-01-27 | 2021-07-06 | International Business Machines Corporation | Throttling a point-in-time snapshot copy operation within a data consistency application |
| US11327858B2 (en) * | 2020-08-11 | 2022-05-10 | Seagate Technology Llc | Preserving data integrity during controller failure |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US6195761B1 (en) * | 1997-12-31 | 2001-02-27 | Emc Corporation | Method and apparatus for identifying and repairing mismatched data |
| US20070294568A1 (en) * | 2006-06-02 | 2007-12-20 | Yoshimasa Kanda | Storage system and method of managing data using the same |
| US20080243952A1 (en) * | 2007-03-28 | 2008-10-02 | Erez Webman | Group Stamping Style Asynchronous Replication Utilizing A Loosely-Accurate Global Clock |
| CN101751230A (en) * | 2009-12-29 | 2010-06-23 | 成都市华为赛门铁克科技有限公司 | Equipment and method for calibrating time stamp of I/O (input/output) data |
| CN102239479A (en) * | 2008-12-18 | 2011-11-09 | Lsi公司 | Method for implementing multi-array consistency groups using a write queuing mechanism |
Family Cites Families (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US6842825B2 (en) * | 2002-08-07 | 2005-01-11 | International Business Machines Corporation | Adjusting timestamps to preserve update timing information for cached data objects |
| US7133986B2 (en) * | 2003-09-29 | 2006-11-07 | International Business Machines Corporation | Method, system, and program for forming a consistency group |
| US8788768B2 (en) | 2010-09-29 | 2014-07-22 | International Business Machines Corporation | Maintaining mirror and storage system copies of volumes at multiple remote sites |
-
2013
- 2013-05-23 US US13/901,082 patent/US9280296B2/en active Active
-
2014
- 2014-05-22 CN CN201410220136.3A patent/CN104182297B/en not_active Expired - Fee Related
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US6195761B1 (en) * | 1997-12-31 | 2001-02-27 | Emc Corporation | Method and apparatus for identifying and repairing mismatched data |
| US20070294568A1 (en) * | 2006-06-02 | 2007-12-20 | Yoshimasa Kanda | Storage system and method of managing data using the same |
| US20080243952A1 (en) * | 2007-03-28 | 2008-10-02 | Erez Webman | Group Stamping Style Asynchronous Replication Utilizing A Loosely-Accurate Global Clock |
| CN102239479A (en) * | 2008-12-18 | 2011-11-09 | Lsi公司 | Method for implementing multi-array consistency groups using a write queuing mechanism |
| CN101751230A (en) * | 2009-12-29 | 2010-06-23 | 成都市华为赛门铁克科技有限公司 | Equipment and method for calibrating time stamp of I/O (input/output) data |
Also Published As
| Publication number | Publication date |
|---|---|
| US9280296B2 (en) | 2016-03-08 |
| US20140351534A1 (en) | 2014-11-27 |
| CN104182297B (en) | 2017-10-13 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN104182297A (en) | Method and system used for recovery from failure of primary storage volumes | |
| US8788772B2 (en) | Maintaining mirror and storage system copies of volumes at multiple remote sites | |
| US9563517B1 (en) | Cloud snapshots | |
| US9940205B2 (en) | Virtual point in time access between snapshots | |
| US9176823B2 (en) | Data transfer and recovery process | |
| US9772789B1 (en) | Alignment fixing on a data protection system during continuous data replication to deduplicated storage | |
| US9389800B1 (en) | Synthesizing virtual machine disk backups | |
| US9563655B2 (en) | Zero and near-zero data loss database backup and recovery | |
| US9600553B1 (en) | Distributed replication in cluster environments | |
| US9535801B1 (en) | Xcopy in journal based replication | |
| US8108364B2 (en) | Representation of system clock changes in time based file systems | |
| US9672117B1 (en) | Method and system for star replication using multiple replication technologies | |
| US20160026540A1 (en) | Merging an out of synchronization indicator and a change recording indicator in response to a failure in consistency group formation | |
| US20140108345A1 (en) | Exchanging locations of an out of synchronization indicator and a change recording indicator via pointers | |
| US10430290B2 (en) | Method and system for star replication using multiple replication technologies | |
| US7761431B2 (en) | Consolidating session information for a cluster of sessions in a coupled session environment | |
| JP2007511008A (en) | Hybrid real-time data replication | |
| US10372554B1 (en) | Verification and restore of replicated data using a cloud storing chunks of data and a plurality of hashes | |
| US10484179B1 (en) | Data consistency in an encrypted replication environment | |
| US10235145B1 (en) | Distributed scale-out replication | |
| US20160342484A1 (en) | Point in Time Recovery on a Database | |
| US9015433B2 (en) | Resiliency with a destination volume in a replication environment | |
| US10671596B1 (en) | Consistency determination | |
| CN113535430B (en) | Application data read-write separation method, device, computer equipment and storage medium | |
| US11500740B2 (en) | Continuous data protection |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| C06 | Publication | ||
| PB01 | Publication | ||
| C10 | Entry into substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant | ||
| TR01 | Transfer of patent right |
Effective date of registration: 20171114 Address after: Grand Cayman, Cayman Islands Patentee after: GLOBALFOUNDRIES INC. Address before: American New York Patentee before: Core USA second LLC Effective date of registration: 20171114 Address after: American New York Patentee after: Core USA second LLC Address before: New York grams of Armand Patentee before: International Business Machines Corp. |
|
| TR01 | Transfer of patent right | ||
| TR01 | Transfer of patent right |
Effective date of registration: 20171120 Address after: Grand Cayman, Cayman Islands Patentee after: GLOBALFOUNDRIES INC. Address before: American New York Patentee before: Core USA second LLC Effective date of registration: 20171120 Address after: American New York Patentee after: Core USA second LLC Address before: New York grams of Armand Patentee before: International Business Machines Corp. |
|
| TR01 | Transfer of patent right | ||
| CF01 | Termination of patent right due to non-payment of annual fee |
Granted publication date: 20171013 Termination date: 20210522 |
|
| CF01 | Termination of patent right due to non-payment of annual fee |